app.py

from fastai.vision.all import *
from io import BytesIO
import requests
import streamlit as st

import numpy as np
import torch
import time
import cv2
from numpy import random
from models.experimental import attempt_load
from utils.general import check_img_size, check_requirements, check_imshow, non_max_suppression, apply_classifier, \
    scale_coords, xyxy2xywh, strip_optimizer, set_logging, increment_path
from utils.plots import plot_one_box

def letterbox(img, new_shape=(640, 640), color=(114, 114, 114), auto=True, scaleFill=False, scaleup=True, stride=32):
    # Resize and pad image while meeting stride-multiple constraints
    shape = img.shape[:2]  # current shape [height, width]
    if isinstance(new_shape, int):
        new_shape = (new_shape, new_shape)

    # Scale ratio (new / old)
    r = min(new_shape[0] / shape[0], new_shape[1] / shape[1])
    if not scaleup:  # only scale down, do not scale up (for better test mAP)
        r = min(r, 1.0)

    # Compute padding
    ratio = r, r  # width, height ratios
    new_unpad = int(round(shape[1] * r)), int(round(shape[0] * r))
    dw, dh = new_shape[1] - new_unpad[0], new_shape[0] - new_unpad[1]  # wh padding
    if auto:  # minimum rectangle
        dw, dh = np.mod(dw, stride), np.mod(dh, stride)  # wh padding
    elif scaleFill:  # stretch
        dw, dh = 0.0, 0.0
        new_unpad = (new_shape[1], new_shape[0])
        ratio = new_shape[1] / shape[1], new_shape[0] / shape[0]  # width, height ratios

    dw /= 2  # divide padding into 2 sides
    dh /= 2

    if shape[::-1] != new_unpad:  # resize
        img = cv2.resize(img, new_unpad, interpolation=cv2.INTER_LINEAR)
    top, bottom = int(round(dh - 0.1)), int(round(dh + 0.1))
    left, right = int(round(dw - 0.1)), int(round(dw + 0.1))
    img = cv2.copyMakeBorder(img, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color)  # add border
    return img, ratio, (dw, dh)

def detect_modify(img0, model, conf=0.4, imgsz=640, conf_thres = 0.25, iou_thres=0.45):
    st.image(img0, caption="Your image", use_column_width=True)

    stride = int(model.stride.max())  # model stride
    imgsz = check_img_size(imgsz, s=stride)  # check img_size

    # Padded resize
    img0 = cv2.cvtColor(np.asarray(img0), cv2.COLOR_RGB2BGR)
    img = letterbox(img0, imgsz, stride=stride)[0]
    # Convert
    img = img[:, :, ::-1].transpose(2, 0, 1)  # BGR to RGB, to 3x416x416
    img = np.ascontiguousarray(img)

    
    # Get names and colors
    names = model.module.names if hasattr(model, 'module') else model.names
    colors = [[random.randint(0, 255) for _ in range(3)] for _ in names]

    # Run inference
    old_img_w = old_img_h = imgsz
    old_img_b = 1

    t0 = time.time()
    img = torch.from_numpy(img).to(device)
    # img /= 255.0  # 0 - 255 to 0.0 - 1.0
    img = img/255.0
    if img.ndimension() == 3:
        img = img.unsqueeze(0)

    # Inference
    # t1 = time_synchronized()
    with torch.no_grad():   # Calculating gradients would cause a GPU memory leak
        pred = model(img)[0]
    # t2 = time_synchronized()

    # Apply NMS
    pred = non_max_suppression(pred, conf_thres, iou_thres)
    # t3 = time_synchronized()

    # Process detections
    # for i, det in enumerate(pred):  # detections per image
        
    gn = torch.tensor(img0.shape)[[1, 0, 1, 0]]  # normalization gain whwh

    det = pred[0]
    if len(det):
        # Rescale boxes from img_size to im0 size
        det[:, :4] = scale_coords(img.shape[2:], det[:, :4], img0.shape).round()

        # Print results
        s = ''
        for c in det[:, -1].unique():
            n = (det[:, -1] == c).sum()  # detections per class
            s += f"{n} {names[int(c)]}{'s' * (n > 1)}, "  # add to string

        # Write results
        for *xyxy, conf, cls in reversed(det):
            label = f'{names[int(cls)]} {conf:.2f}'
            plot_one_box(xyxy, img0, label=label, color=colors[int(cls)], line_thickness=1)

    f"""
    ### Prediction result:
    """
    img0 = cv2.cvtColor(np.asarray(img0), cv2.COLOR_BGR2RGB)
    st.image(img0, caption="Prediction Result", use_column_width=True)

#set paramters
weight_path = './best.pt'
imgsz = 640
conf = 0.4
conf_thres = 0.25
iou_thres=0.45
device = torch.device("cpu")
path = "./"

# Load model
model = attempt_load(weight_path, map_location=torch.device('cpu'))  # load FP32 model

"""
# YOLOv7
This is a object detection model for crosswalk.
"""
option = st.radio("", ["Upload Image", "Image URL"])

if option == "Upload Image":
    uploaded_file = st.file_uploader("Please upload an crosswalk image.")

    if uploaded_file is not None:
        img = PILImage.create(uploaded_file)
        detect_modify(img, model, conf=conf, imgsz=imgsz, conf_thres=conf_thres, iou_thres=iou_thres)
else:
    url = st.text_input("Please input a url.")
    if url != "":
        try:
            response = requests.get(url)
            pil_img = PILImage.create(BytesIO(response.content))
            detect_modify(pil_img, model, conf=conf, imgsz=imgsz, conf_thres=conf_thres, iou_thres=iou_thres)
        except:
            st.text("Problem reading image from", url)